© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 34-GEMMASCOPE-2-TRANSCODER-262K
    7. 165439
    Prev
    Next
    INDEX
    Explanations

    cooking measurements

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_34_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     cocktail
    0.50
     коктей
    0.46
     cocktails
    0.44
     Cocktail
    0.43
     excepción
    0.41
     variational
    0.40
    ដំណ
    0.38
    除
    0.37
     اصلي
    0.37
     Neo
    0.37
    POSITIVE LOGITS
    搠
    0.46
    measurable
    0.42
    metric
    0.38
    Hr
    0.38
    ிருக்கிறார்
    0.38
    ще
    0.37
    fol
    0.37
     साढ़े
    0.37
    两人
    0.37
    reck
    0.36
    Activations Density 0.007%

    No Known Activations